© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209347
    Prev
    Next
    INDEX
    Explanations

    complexes and machines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     četiri
    0.36
    }*/
    0.35
     ouvert
    0.35
     তিনটি
    0.34
     voltou
    0.34
     Drei
    0.34
     സംഘ
    0.33
     trois
    0.33
     মার্চ
    0.33
     zatím
    0.33
    POSITIVE LOGITS
    혀
    0.38
    ю
    0.35
    жаться
    0.34
    铄
    0.33
    дим
    0.33
    ياء
    0.32
     overlaps
    0.32
    க்கொ
    0.32
    refund
    0.32
     Terence
    0.31
    Activations Density 0.001%

    No Known Activations